Mihyeon Kim
4 papers · 2023–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (2) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (12) π§ Keyword Pioneer π£ Hot Topic Early Bird
π
Cross-Pollinator
(15)
Conferences
EMNLP (2)
AAAI (1)
NAACL (1)
Top co-authors
Keywords
model compression
(1)
adversarial robustness
(1)
attention mechanism
(1)
multimodal learning
(1)
machine unlearning
(1)
model forgetting
(1)
loss landscape
(1)
gradient descent
(1)
document classification
(1)
adversarial attack
(1)
bias mitigation
(1)
spurious correlation
(1)
vision-language model
(1)
numerical stability
(1)
token pruning
(1)
pre-trained language model
(1)
ordinary differential equation
(1)
token compression
(1)
fuzzy logic
(1)
efficient attention
(1)
Papers
Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias
AAAI 2026
See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias
NAACL 2025
IM-BERT: Enhancing Robustness of BERT through the Implicit Euler Method
EMNLP 2024
Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification
EMNLP 2023